Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2601.15115 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915744318488576 |
|---|---|
| author | Yang, Shuonan Zhang, Yuchen Fu, Zeyu |
| author_facet | Yang, Shuonan Zhang, Yuchen Fu, Zeyu |
| contents | Hateful videos pose serious risks by amplifying discrimination, inciting violence, and undermining online safety. Existing training-based hateful video detection methods are constrained by limited training data and lack of interpretability, while directly prompting large vision-language models often struggle to deliver reliable hate detection. To address these challenges, this paper introduces MARS, a training-free Multi-stage Adversarial ReaSoning framework that enables reliable and interpretable hateful content detection. MARS begins with the objective description of video content, establishing a neutral foundation for subsequent analysis. Building on this, it develops evidence-based reasoning that supports potential hateful interpretations, while in parallel incorporating counter-evidence reasoning to capture plausible non-hateful perspectives. Finally, these perspectives are synthesized into a conclusive and explainable decision. Extensive evaluation on two real-world datasets shows that MARS achieves up to 10% improvement under certain backbones and settings compared to other training-free approaches and outperforms state-of-the-art training-based methods on one dataset. In addition, MARS produces human-understandable justifications, thereby supporting compliance oversight and enhancing the transparency of content moderation workflows. The code is available at https://github.com/Multimodal-Intelligence-Lab-MIL/MARS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15115 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Training-Free and Interpretable Hateful Video Detection via Multi-stage Adversarial Reasoning Yang, Shuonan Zhang, Yuchen Fu, Zeyu Computer Vision and Pattern Recognition Hateful videos pose serious risks by amplifying discrimination, inciting violence, and undermining online safety. Existing training-based hateful video detection methods are constrained by limited training data and lack of interpretability, while directly prompting large vision-language models often struggle to deliver reliable hate detection. To address these challenges, this paper introduces MARS, a training-free Multi-stage Adversarial ReaSoning framework that enables reliable and interpretable hateful content detection. MARS begins with the objective description of video content, establishing a neutral foundation for subsequent analysis. Building on this, it develops evidence-based reasoning that supports potential hateful interpretations, while in parallel incorporating counter-evidence reasoning to capture plausible non-hateful perspectives. Finally, these perspectives are synthesized into a conclusive and explainable decision. Extensive evaluation on two real-world datasets shows that MARS achieves up to 10% improvement under certain backbones and settings compared to other training-free approaches and outperforms state-of-the-art training-based methods on one dataset. In addition, MARS produces human-understandable justifications, thereby supporting compliance oversight and enhancing the transparency of content moderation workflows. The code is available at https://github.com/Multimodal-Intelligence-Lab-MIL/MARS. |
| title | Training-Free and Interpretable Hateful Video Detection via Multi-stage Adversarial Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.15115 |